forked from shadowsocks/shadowsocks-libev
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathserver.c
2428 lines (2157 loc) · 73.5 KB
/
server.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* server.c - Provide shadowsocks service
*
* Copyright (C) 2013 - 2019, Max Lv <[email protected]>
*
* This file is part of the shadowsocks-libev.
*
* shadowsocks-libev is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 3 of the License, or
* (at your option) any later version.
*
* shadowsocks-libev is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with shadowsocks-libev; see the file COPYING. If not, see
* <http://www.gnu.org/licenses/>.
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include <sys/stat.h>
#include <sys/types.h>
#include <fcntl.h>
#include <locale.h>
#include <signal.h>
#include <string.h>
#include <strings.h>
#include <time.h>
#include <unistd.h>
#include <getopt.h>
#include <math.h>
#ifndef __MINGW32__
#include <netdb.h>
#include <errno.h>
#include <arpa/inet.h>
#include <netinet/in.h>
#include <pthread.h>
#include <sys/un.h>
#endif
#include <libcork/core.h>
#if defined(HAVE_SYS_IOCTL_H) && defined(HAVE_NET_IF_H) && defined(__linux__)
#include <net/if.h>
#include <sys/ioctl.h>
#define SET_INTERFACE
#endif
#ifdef USE_NFTABLES
#include <ctype.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nf_tables.h>
#include <libmnl/libmnl.h>
#include <libnftnl/set.h>
/* the datatypes enum is picked from libnftables/datatype.h
to avoid to depend libnftables */
enum datatypes {
TYPE_IPADDR = 7,
TYPE_IP6ADDR
};
#endif
#include "netutils.h"
#include "utils.h"
#include "acl.h"
#include "plugin.h"
#include "server.h"
#include "winsock.h"
#include "resolv.h"
#ifndef EAGAIN
#define EAGAIN EWOULDBLOCK
#endif
#ifndef EWOULDBLOCK
#define EWOULDBLOCK EAGAIN
#endif
#ifndef SSMAXCONN
#define SSMAXCONN 1024
#endif
#ifdef USE_NFCONNTRACK_TOS
#ifndef MARK_MAX_PACKET
#define MARK_MAX_PACKET 10
#endif
#ifndef MARK_MASK_PREFIX
#define MARK_MASK_PREFIX 0xDC00
#endif
#endif
static void signal_cb(EV_P_ ev_signal *w, int revents);
static void accept_cb(EV_P_ ev_io *w, int revents);
static void server_send_cb(EV_P_ ev_io *w, int revents);
static void server_recv_cb(EV_P_ ev_io *w, int revents);
static void remote_recv_cb(EV_P_ ev_io *w, int revents);
static void remote_send_cb(EV_P_ ev_io *w, int revents);
static void server_timeout_cb(EV_P_ ev_timer *watcher, int revents);
static remote_t *new_remote(int fd);
static server_t *new_server(int fd, listen_ctx_t *listener);
static remote_t *connect_to_remote(EV_P_ struct addrinfo *res,
server_t *server);
static void free_remote(remote_t *remote);
static void close_and_free_remote(EV_P_ remote_t *remote);
static void free_server(server_t *server);
static void close_and_free_server(EV_P_ server_t *server);
static void resolv_cb(struct sockaddr *addr, void *data);
static void resolv_free_cb(void *data);
int verbose = 0;
int reuse_port = 0;
int tcp_incoming_sndbuf = 0;
int tcp_incoming_rcvbuf = 0;
int tcp_outgoing_sndbuf = 0;
int tcp_outgoing_rcvbuf = 0;
int is_bind_local_addr = 0;
struct sockaddr_storage local_addr_v4;
struct sockaddr_storage local_addr_v6;
static crypto_t *crypto;
static int acl = 0;
static int mode = TCP_ONLY;
static int ipv6first = 0;
int fast_open = 0;
static int no_delay = 0;
static int ret_val = 0;
#ifdef HAVE_SETRLIMIT
static int nofile = 0;
#endif
static int remote_conn = 0;
static int server_conn = 0;
static char *plugin = NULL;
static char *remote_port = NULL;
static char *manager_addr = NULL;
uint64_t tx = 0;
uint64_t rx = 0;
#ifndef __MINGW32__
ev_timer stat_update_watcher;
#endif
static struct ev_signal sigint_watcher;
static struct ev_signal sigterm_watcher;
#ifndef __MINGW32__
static struct ev_signal sigchld_watcher;
#else
static struct plugin_watcher_t {
ev_io io;
SOCKET fd;
uint16_t port;
int valid;
} plugin_watcher;
#endif
static struct cork_dllist connections;
#ifndef __MINGW32__
static void
stat_update_cb(EV_P_ ev_timer *watcher, int revents)
{
struct sockaddr_un svaddr, claddr;
int sfd = -1;
size_t msgLen;
char resp[SOCKET_BUF_SIZE];
if (verbose) {
LOGI("update traffic stat: tx: %" PRIu64 " rx: %" PRIu64 "", tx, rx);
}
snprintf(resp, SOCKET_BUF_SIZE, "stat: {\"%s\":%" PRIu64 "}", remote_port, tx + rx);
msgLen = strlen(resp) + 1;
ss_addr_t ip_addr = { .host = NULL, .port = NULL };
parse_addr(manager_addr, &ip_addr);
if (ip_addr.host == NULL || ip_addr.port == NULL) {
sfd = socket(AF_UNIX, SOCK_DGRAM, 0);
if (sfd == -1) {
ERROR("stat_socket");
return;
}
memset(&claddr, 0, sizeof(struct sockaddr_un));
claddr.sun_family = AF_UNIX;
snprintf(claddr.sun_path, sizeof(claddr.sun_path), "/tmp/shadowsocks.%s", remote_port);
unlink(claddr.sun_path);
if (bind(sfd, (struct sockaddr *)&claddr, sizeof(struct sockaddr_un)) == -1) {
ERROR("stat_bind");
close(sfd);
return;
}
memset(&svaddr, 0, sizeof(struct sockaddr_un));
svaddr.sun_family = AF_UNIX;
strncpy(svaddr.sun_path, manager_addr, sizeof(svaddr.sun_path) - 1);
if (sendto(sfd, resp, strlen(resp) + 1, 0, (struct sockaddr *)&svaddr,
sizeof(struct sockaddr_un)) != msgLen) {
ERROR("stat_sendto");
close(sfd);
return;
}
unlink(claddr.sun_path);
} else {
struct sockaddr_storage storage;
memset(&storage, 0, sizeof(struct sockaddr_storage));
if (get_sockaddr(ip_addr.host, ip_addr.port, &storage, 0, ipv6first) == -1) {
ERROR("failed to parse the manager addr");
return;
}
sfd = socket(storage.ss_family, SOCK_DGRAM, 0);
if (sfd == -1) {
ERROR("stat_socket");
return;
}
size_t addr_len = get_sockaddr_len((struct sockaddr *)&storage);
if (sendto(sfd, resp, strlen(resp) + 1, 0, (struct sockaddr *)&storage,
addr_len) != msgLen) {
ERROR("stat_sendto");
close(sfd);
return;
}
}
close(sfd);
}
#endif
static void
free_connections(struct ev_loop *loop)
{
struct cork_dllist_item *curr, *next;
cork_dllist_foreach_void(&connections, curr, next) {
server_t *server = cork_container_of(curr, server_t, entries);
remote_t *remote = server->remote;
close_and_free_server(loop, server);
close_and_free_remote(loop, remote);
}
}
static char *
get_peer_name(int fd)
{
static char peer_name[INET6_ADDRSTRLEN] = { 0 };
struct sockaddr_storage addr;
socklen_t len = sizeof(struct sockaddr_storage);
memset(&addr, 0, len);
memset(peer_name, 0, INET6_ADDRSTRLEN);
int err = getpeername(fd, (struct sockaddr *)&addr, &len);
if (err == 0) {
if (addr.ss_family == AF_INET) {
struct sockaddr_in *s = (struct sockaddr_in *)&addr;
inet_ntop(AF_INET, &s->sin_addr, peer_name, INET_ADDRSTRLEN);
} else if (addr.ss_family == AF_INET6) {
struct sockaddr_in6 *s = (struct sockaddr_in6 *)&addr;
inet_ntop(AF_INET6, &s->sin6_addr, peer_name, INET6_ADDRSTRLEN);
}
} else {
return NULL;
}
return peer_name;
}
static void
stop_server(EV_P_ server_t *server)
{
server->stage = STAGE_STOP;
}
#ifdef USE_NFTABLES
struct nftbl_set_info {
uint32_t family;
char *table;
char *name;
uint32_t type;
}* nftbl_badip_sets[16];
static struct nftnl_set *
nftbl_build_set(const char* table, const char* name, void* addr, size_t len)
{
struct nftnl_set *set = nftnl_set_alloc();
if (set == NULL) return NULL;
nftnl_set_set_str(set, NFTNL_SET_TABLE, table);
nftnl_set_set_str(set, NFTNL_SET_NAME, name);
struct nftnl_set_elem *elem = nftnl_set_elem_alloc();
if (elem == NULL) {
nftnl_set_free(set);
return NULL;
}
nftnl_set_elem_set(elem, NFTNL_SET_ELEM_KEY, addr, len);
nftnl_set_elem_add(set, elem);
return set;
}
static uint32_t
nftbl_build_nlmsg(void* buf, size_t *len, uint32_t family,
struct nftnl_set *set)
{
uint32_t seq = time(NULL);
struct nlmsghdr *nlh;
struct mnl_nlmsg_batch *batch = mnl_nlmsg_batch_start(buf, *len);
nftnl_batch_begin(mnl_nlmsg_batch_current(batch), seq);
mnl_nlmsg_batch_next(batch);
nlh = nftnl_nlmsg_build_hdr(mnl_nlmsg_batch_current(batch),
NFT_MSG_NEWSETELEM, family,
NLM_F_CREATE | NLM_F_EXCL | NLM_F_ACK,
++seq);
nftnl_set_elems_nlmsg_build_payload(nlh, set);
mnl_nlmsg_batch_next(batch);
nftnl_batch_end(mnl_nlmsg_batch_current(batch), seq + 1);
mnl_nlmsg_batch_next(batch);
*len = mnl_nlmsg_batch_size(batch);
mnl_nlmsg_batch_stop(batch);
return seq;
}
static int
nftbl_send_request(void *request, size_t len, uint32_t seq,
mnl_cb_t cb, void *data)
{
struct mnl_socket *nl = mnl_socket_open(NETLINK_NETFILTER);
if (nl == NULL) return -1;
int ret = -1;
uint8_t buf[MNL_SOCKET_BUFFER_SIZE];
if (mnl_socket_bind(nl, 0, MNL_SOCKET_AUTOPID) == 0 &&
mnl_socket_sendto(nl, request, len) >= 0) {
uint32_t portid = mnl_socket_get_portid(nl);
while ((ret = mnl_socket_recvfrom(nl, buf, sizeof(buf))) > 0) {
ret = mnl_cb_run(buf, ret, seq, portid, cb, data);
if (ret != MNL_CB_OK)
break;
}
mnl_socket_close(nl);
}
return ret;
}
static void
nftbl_report_addr(const struct sockaddr* addr)
{
uint32_t type;
void* data;
size_t size;
if (addr->sa_family == AF_INET) {
type = TYPE_IPADDR;
data = &((struct sockaddr_in*)addr)->sin_addr;
size = sizeof(struct in_addr);
} else if (addr->sa_family == AF_INET6) {
type = TYPE_IP6ADDR;
data = &((struct sockaddr_in6*)addr)->sin6_addr;
size = sizeof(struct in6_addr);
} else {
return;
}
char buf[MNL_SOCKET_BUFFER_SIZE];
for (int i = 0; nftbl_badip_sets[i]; ++i) {
struct nftbl_set_info* si = nftbl_badip_sets[i];
struct nftnl_set *set;
if (si->type == type &&
(set = nftbl_build_set(si->table, si->name, data, size))) {
size_t len = sizeof(buf);
uint32_t seq = nftbl_build_nlmsg(buf, &len, si->family, set);
nftnl_set_free(set);
if (nftbl_send_request(buf, len, seq, NULL, NULL) < 0 &&
errno != EEXIST)
ERROR("nftbl_report_addr");
}
}
}
static int
nftbl_check_cb(const struct nlmsghdr *nlh, void *data)
{
struct nftnl_set *set = (struct nftnl_set*)data;
if (nftnl_set_nlmsg_parse(nlh, set) < 0)
return MNL_CB_ERROR;
uint32_t type = nftnl_set_get_u32(set, NFTNL_SET_KEY_TYPE);
if (type != TYPE_IPADDR && type != TYPE_IP6ADDR)
return MNL_CB_OK;
uint32_t len;
const char *name = nftnl_set_get_data(set, NFTNL_SET_NAME, &len);
for (int i = 0; nftbl_badip_sets[i]; ++i) {
struct nftbl_set_info* si = nftbl_badip_sets[i];
if (!memcmp(name, si->name, len)) {
name = nftnl_set_get_data(set, NFTNL_SET_TABLE, &len);
if (!si->table) {
size_t l = strlen(si->name) + 1;
si = realloc(si, sizeof(*si) + l + len);
si->name = (char*)(si + 1);
si->table = memcpy(si->name + l, name, len);
nftbl_badip_sets[i] = si;
} else if (memcmp(name, si->table, len)) {
continue; /* table name not match */
}
si->family = nftnl_set_get_u32(set, NFTNL_SET_FAMILY);
si->type = type;
}
}
return MNL_CB_OK;
}
static int
nftbl_check(void)
{
struct nftnl_set *set = nftnl_set_alloc();
if (!set) return -1;
int ret;
char buf[MNL_SOCKET_BUFFER_SIZE];
uint32_t seq = time(NULL);
struct nlmsghdr *nlh;
nlh = nftnl_set_nlmsg_build_hdr(buf, NFT_MSG_GETSET, NFPROTO_UNSPEC,
NLM_F_DUMP|NLM_F_ACK, seq);
nftnl_set_nlmsg_build_payload(nlh, set);
ret = nftbl_send_request(nlh, nlh->nlmsg_len, seq, nftbl_check_cb, set);
nftnl_set_free(set);
if (ret < 0) return ret;
for (int i = 0; nftbl_badip_sets[i]; ++i) {
struct nftbl_set_info* si = nftbl_badip_sets[i];
if (si->family == NFPROTO_UNSPEC) {
if (si->table)
LOGE("set '%s' not found in table '%s'", si->name, si->table);
else
LOGE("set '%s' not found", si->name);
ret = -1;
}
}
if (ret < 0)
FATAL("Check nftables configuration.");
return ret;
}
static int
nftbl_init(const char* set_str)
{
struct nftbl_set_info* si;
const char *p0 = set_str, *p = p0, *d = NULL;
int i = 0;
do {
if (*p == ':') {
d = p;
} else if (*p == ',' || *p == '\0') {
size_t l = p - p0 + 1;
si = malloc(sizeof(*si) + l);
memset(si, 0, sizeof(*si));
si->name = memcpy(si + 1, p0, l);
si->name[l - 1] = '\0';
if (d) {
si->table = si->name;
si->name = si->table + (d - p0);
*(si->name++) = '\0';
d = NULL;
}
nftbl_badip_sets[i++] = si;
if (i == sizeof(nftbl_badip_sets) / sizeof(*si) - 1)
break;
while (*p && isspace(*(++p)));
p0 = p;
}
} while (*(p++));
return nftbl_check();
}
#endif
static void
report_addr(int fd, const char *info)
{
char *peer_name;
peer_name = get_peer_name(fd);
if (peer_name != NULL) {
LOGE("failed to handshake with %s: %s", peer_name, info);
}
#ifdef USE_NFTABLES
struct sockaddr_in6 addr;
socklen_t len = sizeof(struct sockaddr_in6);
if (!getpeername(fd, (struct sockaddr *)&addr, &len))
nftbl_report_addr((struct sockaddr *)&addr);
#endif
}
int
setfastopen(int fd)
{
int s = 0;
#ifdef TCP_FASTOPEN
if (fast_open) {
#if defined(__APPLE__) || defined(__MINGW32__)
int opt = 1;
#else
int opt = 5;
#endif
s = setsockopt(fd, IPPROTO_TCP, TCP_FASTOPEN, &opt, sizeof(opt));
if (s == -1) {
if (errno == EPROTONOSUPPORT || errno == ENOPROTOOPT) {
LOGE("fast open is not supported on this platform");
fast_open = 0;
} else {
ERROR("setsockopt");
}
}
}
#endif
return s;
}
#ifndef __MINGW32__
int
setnonblocking(int fd)
{
int flags;
if (-1 == (flags = fcntl(fd, F_GETFL, 0))) {
flags = 0;
}
return fcntl(fd, F_SETFL, flags | O_NONBLOCK);
}
#endif
int
create_and_bind(const char *host, const char *port, int mptcp)
{
struct addrinfo hints;
struct addrinfo *result, *rp, *ipv4v6bindall;
int s, listen_sock = -1;
memset(&hints, 0, sizeof(struct addrinfo));
hints.ai_family = AF_UNSPEC; /* Return IPv4 and IPv6 choices */
hints.ai_socktype = SOCK_STREAM; /* We want a TCP socket */
hints.ai_flags = AI_PASSIVE | AI_ADDRCONFIG; /* For wildcard IP address */
hints.ai_protocol = IPPROTO_TCP;
result = NULL;
s = getaddrinfo(host, port, &hints, &result);
if (s != 0) {
LOGE("failed to resolve server name %s", host);
return -1;
}
if (result == NULL) {
LOGE("Cannot bind");
return -1;
}
rp = result;
/*
* On Linux, with net.ipv6.bindv6only = 0 (the default), getaddrinfo(NULL) with
* AI_PASSIVE returns 0.0.0.0 and :: (in this order). AI_PASSIVE was meant to
* return a list of addresses to listen on, but it is impossible to listen on
* 0.0.0.0 and :: at the same time, if :: implies dualstack mode.
*/
if (!host) {
ipv4v6bindall = result;
/* Loop over all address infos found until a IPV6 address is found. */
while (ipv4v6bindall) {
if (ipv4v6bindall->ai_family == AF_INET6) {
rp = ipv4v6bindall; /* Take first IPV6 address available */
break;
}
ipv4v6bindall = ipv4v6bindall->ai_next; /* Get next address info, if any */
}
}
for (/*rp = result*/; rp != NULL; rp = rp->ai_next) {
int protocol = rp->ai_protocol;
if (mptcp < 0) {
protocol = IPPROTO_MPTCP; // Enable upstream MPTCP
}
listen_sock = socket(rp->ai_family, rp->ai_socktype, protocol);
if (listen_sock == -1) {
continue;
}
if (rp->ai_family == AF_INET6) {
int opt = host ? 1 : 0;
setsockopt(listen_sock, IPPROTO_IPV6, IPV6_V6ONLY, &opt, sizeof(opt));
}
int opt = 1;
setsockopt(listen_sock, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt));
#ifdef SO_NOSIGPIPE
setsockopt(listen_sock, SOL_SOCKET, SO_NOSIGPIPE, &opt, sizeof(opt));
#endif
if (reuse_port) {
int err = set_reuseport(listen_sock);
if (err == 0) {
LOGI("tcp port reuse enabled");
}
}
if (tcp_incoming_sndbuf > 0) {
setsockopt(listen_sock, SOL_SOCKET, SO_SNDBUF, &tcp_incoming_sndbuf, sizeof(int));
}
if (tcp_incoming_rcvbuf > 0) {
setsockopt(listen_sock, SOL_SOCKET, SO_RCVBUF, &tcp_incoming_rcvbuf, sizeof(int));
}
// Enable out-of-tree mptcp
if (mptcp == 1) {
int i = 0;
while ((mptcp = mptcp_enabled_values[i]) > 0) {
int err = setsockopt(listen_sock, IPPROTO_TCP, mptcp, &opt, sizeof(opt));
if (err != -1) {
break;
}
i++;
}
if (mptcp == 0) {
ERROR("failed to enable out-of-tree multipath TCP");
}
}
s = bind(listen_sock, rp->ai_addr, rp->ai_addrlen);
if (s == 0) {
/* We managed to bind successfully! */
break;
} else {
ERROR("bind");
FATAL("failed to bind address");
}
close(listen_sock);
listen_sock = -1;
}
freeaddrinfo(result);
return listen_sock;
}
static remote_t *
connect_to_remote(EV_P_ struct addrinfo *res,
server_t *server)
{
int sockfd;
#ifdef SET_INTERFACE
const char *iface = server->listen_ctx->iface;
#endif
if (acl) {
char ipstr[INET6_ADDRSTRLEN];
memset(ipstr, 0, INET6_ADDRSTRLEN);
if (res->ai_addr->sa_family == AF_INET) {
struct sockaddr_in s;
memcpy(&s, res->ai_addr, sizeof(struct sockaddr_in));
inet_ntop(AF_INET, &s.sin_addr, ipstr, INET_ADDRSTRLEN);
} else if (res->ai_addr->sa_family == AF_INET6) {
struct sockaddr_in6 s;
memcpy(&s, res->ai_addr, sizeof(struct sockaddr_in6));
inet_ntop(AF_INET6, &s.sin6_addr, ipstr, INET6_ADDRSTRLEN);
}
if (outbound_block_match_host(ipstr) == 1) {
if (verbose)
LOGI("outbound blocked %s", ipstr);
return NULL;
}
}
// initialize remote socks
sockfd = socket(res->ai_family, res->ai_socktype, res->ai_protocol);
if (sockfd == -1) {
ERROR("socket");
close(sockfd);
return NULL;
}
int opt = 1;
setsockopt(sockfd, SOL_TCP, TCP_NODELAY, &opt, sizeof(opt));
#ifdef SO_NOSIGPIPE
setsockopt(sockfd, SOL_SOCKET, SO_NOSIGPIPE, &opt, sizeof(opt));
#endif
setsockopt(sockfd, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt));
if (tcp_outgoing_sndbuf > 0) {
setsockopt(sockfd, SOL_SOCKET, SO_SNDBUF, &tcp_outgoing_sndbuf, sizeof(int));
}
if (tcp_outgoing_rcvbuf > 0) {
setsockopt(sockfd, SOL_SOCKET, SO_RCVBUF, &tcp_outgoing_rcvbuf, sizeof(int));
}
// setup remote socks
if (setnonblocking(sockfd) == -1)
ERROR("setnonblocking");
if (is_bind_local_addr) {
struct sockaddr_storage *local_addr =
res->ai_family == AF_INET ? &local_addr_v4 : &local_addr_v6;
if (res->ai_family == local_addr->ss_family) {
if (bind_to_addr(local_addr, sockfd) == -1) {
ERROR("bind_to_addr");
FATAL("cannot bind socket");
return NULL;
}
}
}
#ifdef SET_INTERFACE
if (iface) {
if (setinterface(sockfd, iface) == -1) {
ERROR("setinterface");
close(sockfd);
return NULL;
}
}
#endif
remote_t *remote = new_remote(sockfd);
if (fast_open) {
#if defined(MSG_FASTOPEN) && !defined(TCP_FASTOPEN_CONNECT)
int s = -1;
s = sendto(sockfd, server->buf->data + server->buf->idx, server->buf->len,
MSG_FASTOPEN, res->ai_addr, res->ai_addrlen);
#elif defined(TCP_FASTOPEN_WINSOCK)
DWORD s = -1;
DWORD err = 0;
do {
int optval = 1;
// Set fast open option
if (setsockopt(sockfd, IPPROTO_TCP, TCP_FASTOPEN,
&optval, sizeof(optval)) != 0) {
ERROR("setsockopt");
break;
}
// Load ConnectEx function
LPFN_CONNECTEX ConnectEx = winsock_getconnectex();
if (ConnectEx == NULL) {
LOGE("Cannot load ConnectEx() function");
err = WSAENOPROTOOPT;
break;
}
// ConnectEx requires a bound socket
if (winsock_dummybind(sockfd, res->ai_addr) != 0) {
ERROR("bind");
break;
}
// Call ConnectEx to send data
memset(&remote->olap, 0, sizeof(remote->olap));
remote->connect_ex_done = 0;
if (ConnectEx(sockfd, res->ai_addr, res->ai_addrlen,
server->buf->data + server->buf->idx,
server->buf->len, &s, &remote->olap)) {
remote->connect_ex_done = 1;
break;
}
// XXX: ConnectEx pending, check later in remote_send
if (WSAGetLastError() == ERROR_IO_PENDING) {
err = CONNECT_IN_PROGRESS;
break;
}
ERROR("ConnectEx");
} while (0);
// Set error number
if (err) {
SetLastError(err);
}
#else
int s = -1;
#if defined(TCP_FASTOPEN_CONNECT)
int optval = 1;
if (setsockopt(sockfd, IPPROTO_TCP, TCP_FASTOPEN_CONNECT,
(void *)&optval, sizeof(optval)) < 0)
FATAL("failed to set TCP_FASTOPEN_CONNECT");
s = connect(sockfd, res->ai_addr, res->ai_addrlen);
#elif defined(CONNECT_DATA_IDEMPOTENT)
struct sockaddr_in sa;
memcpy(&sa, res->ai_addr, sizeof(struct sockaddr_in));
sa.sin_len = sizeof(struct sockaddr_in);
sa_endpoints_t endpoints;
memset((char *)&endpoints, 0, sizeof(endpoints));
endpoints.sae_dstaddr = (struct sockaddr *)&sa;
endpoints.sae_dstaddrlen = res->ai_addrlen;
s = connectx(sockfd, &endpoints, SAE_ASSOCID_ANY, CONNECT_DATA_IDEMPOTENT,
NULL, 0, NULL, NULL);
#else
FATAL("fast open is not enabled in this build");
#endif
if (s == 0)
s = send(sockfd, server->buf->data + server->buf->idx, server->buf->len, 0);
#endif
if (s == -1) {
if (errno == CONNECT_IN_PROGRESS) {
// The remote server doesn't support tfo or it's the first connection to the server.
// It will automatically fall back to conventional TCP.
} else if (errno == EOPNOTSUPP || errno == EPROTONOSUPPORT ||
errno == ENOPROTOOPT) {
// Disable fast open as it's not supported
fast_open = 0;
LOGE("fast open is not supported on this platform");
} else {
ERROR("fast_open_connect");
}
} else {
server->buf->idx += s;
server->buf->len -= s;
}
}
if (!fast_open) {
int r = connect(sockfd, res->ai_addr, res->ai_addrlen);
if (r == -1 && errno != CONNECT_IN_PROGRESS) {
ERROR("connect");
close_and_free_remote(EV_A_ remote);
return NULL;
}
}
return remote;
}
#ifdef USE_NFCONNTRACK_TOS
int
setMarkDscpCallback(enum nf_conntrack_msg_type type, struct nf_conntrack *ct, void *data)
{
server_t *server = (server_t *)data;
struct dscptracker *tracker = server->tracker;
tracker->mark = nfct_get_attr_u32(ct, ATTR_MARK);
if ((tracker->mark & 0xff00) == MARK_MASK_PREFIX) {
// Extract DSCP value from mark value
tracker->dscp = tracker->mark & 0x00ff;
int tos = (tracker->dscp) << 2;
if (setsockopt(server->fd, IPPROTO_IP, IP_TOS, &tos, sizeof(tos)) != 0) {
ERROR("iptable setsockopt IP_TOS");
}
}
return NFCT_CB_CONTINUE;
}
void
conntrackQuery(server_t *server)
{
struct dscptracker *tracker = server->tracker;
if (tracker && tracker->ct) {
// Trying query mark from nf conntrack
struct nfct_handle *h = nfct_open(CONNTRACK, 0);
if (h) {
nfct_callback_register(h, NFCT_T_ALL, setMarkDscpCallback, (void *)server);
int x = nfct_query(h, NFCT_Q_GET, tracker->ct);
if (x == -1) {
LOGE("QOS: Failed to retrieve connection mark %s", strerror(errno));
}
nfct_close(h);
} else {
LOGE("QOS: Failed to open conntrack handle for upstream netfilter mark retrieval.");
}
}
}
void
setTosFromConnmark(remote_t *remote, server_t *server)
{
if (server->tracker && server->tracker->ct) {
if (server->tracker->mark == 0 && server->tracker->packet_count < MARK_MAX_PACKET) {
server->tracker->packet_count++;
conntrackQuery(server);
}
} else {
socklen_t len;
struct sockaddr_storage sin;
len = sizeof(sin);
if (getpeername(remote->fd, (struct sockaddr *)&sin, &len) == 0) {
struct sockaddr_storage from_addr;
len = sizeof from_addr;
if (getsockname(remote->fd, (struct sockaddr *)&from_addr, &len) == 0) {
if ((server->tracker = (struct dscptracker *)ss_malloc(sizeof(struct dscptracker)))) {
if ((server->tracker->ct = nfct_new())) {
// Build conntrack query SELECT
if (from_addr.ss_family == AF_INET) {
struct sockaddr_in *src = (struct sockaddr_in *)&from_addr;
struct sockaddr_in *dst = (struct sockaddr_in *)&sin;
nfct_set_attr_u8(server->tracker->ct, ATTR_L3PROTO, AF_INET);
nfct_set_attr_u32(server->tracker->ct, ATTR_IPV4_DST, dst->sin_addr.s_addr);
nfct_set_attr_u32(server->tracker->ct, ATTR_IPV4_SRC, src->sin_addr.s_addr);
nfct_set_attr_u16(server->tracker->ct, ATTR_PORT_DST, dst->sin_port);
nfct_set_attr_u16(server->tracker->ct, ATTR_PORT_SRC, src->sin_port);
} else if (from_addr.ss_family == AF_INET6) {
struct sockaddr_in6 *src = (struct sockaddr_in6 *)&from_addr;
struct sockaddr_in6 *dst = (struct sockaddr_in6 *)&sin;
nfct_set_attr_u8(server->tracker->ct, ATTR_L3PROTO, AF_INET6);
nfct_set_attr(server->tracker->ct, ATTR_IPV6_DST, dst->sin6_addr.s6_addr);
nfct_set_attr(server->tracker->ct, ATTR_IPV6_SRC, src->sin6_addr.s6_addr);
nfct_set_attr_u16(server->tracker->ct, ATTR_PORT_DST, dst->sin6_port);
nfct_set_attr_u16(server->tracker->ct, ATTR_PORT_SRC, src->sin6_port);
}
nfct_set_attr_u8(server->tracker->ct, ATTR_L4PROTO, IPPROTO_TCP);
conntrackQuery(server);
} else {
LOGE("Failed to allocate new conntrack for upstream netfilter mark retrieval.");
server->tracker->ct = NULL;
}
}
}
}
}
}
#endif
static void
server_recv_cb(EV_P_ ev_io *w, int revents)
{
server_ctx_t *server_recv_ctx = (server_ctx_t *)w;
server_t *server = server_recv_ctx->server;
remote_t *remote = NULL;
buffer_t *buf = server->buf;
if (server->stage == STAGE_STREAM) {
remote = server->remote;
buf = remote->buf;
// Only timer the watcher if a valid connection is established
ev_timer_again(EV_A_ & server->recv_ctx->watcher);
}
ssize_t r = recv(server->fd, buf->data, SOCKET_BUF_SIZE, 0);
if (r == 0) {
// connection closed
close_and_free_remote(EV_A_ remote);
close_and_free_server(EV_A_ server);
return;
} else if (r == -1) {
if (errno == EAGAIN || errno == EWOULDBLOCK) {
// no data
// continue to wait for recv
return;
} else {
ERROR("server recv");
close_and_free_remote(EV_A_ remote);
close_and_free_server(EV_A_ server);
return;
}
}
// Ignore any new packet if the server is stopped
if (server->stage == STAGE_STOP) {
return;
}
tx += r;
buf->len = r;
int err = crypto->decrypt(buf, server->d_ctx, SOCKET_BUF_SIZE);
if (err == CRYPTO_ERROR) {
report_addr(server->fd, "authentication error");
stop_server(EV_A_ server);
return;
} else if (err == CRYPTO_NEED_MORE) {
if (server->stage != STAGE_STREAM) {
server->frag++;
}
return;
}
// handshake and transmit data
if (server->stage == STAGE_STREAM) {